OpenPipe/ART

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

View on GitHub →
PythonApache-2.0llmslorareinforcement-learningagentagentic-ai
Stars
10.7k
Δ 7d
+21
Δ 30d
+135
Age
1 yr
Last push
3h ago
11k11k10k10k9.8kJun 7Jul 22Sep 4
90-day star history

Where this sits in the catalog

Most-wanted open issues

Ranked by 👍 reactions. 62 open issues total, checked 2026-08-29.

What Hacker News made of it

Threads that link to or name this project, ranked by points. The comments are where the objections live — the README never argues back.

Alternatives in Agent SDKs & frameworks

DeepSeek Harness: Everything is a Plugin.

211.8k
+10,4097d
TypeScript
3 wk

The agent engineering platform.

145.6k
+4467d
Python
3 yrs

Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory a…

46.8k
+727d
Python
4 yrs

Build, run, and manage agent platforms.

42.0k
+947d
Python
4 yrs

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI P…

37.2k
+1077d
TypeScript
3 yrs

Build and run agents you can see, understand and trust.

30.6k
+7397d
Python
2 yrs